Predicting multiple binding modes using a kernel method based on a vector space model molecular descriptor
- PMID: 20054986
- DOI: 10.1504/ijcbdd.2009.027584
Predicting multiple binding modes using a kernel method based on a vector space model molecular descriptor
Abstract
We describe the use of our Vector Space Model Molecular Descriptor (VSMMD), based on a Vector Space Model (VSM) that is suitable for kernel studies in Quantitative Structure-Activity Relationship (QSAR) modelling. Our experiments provide convincing comparative empirical evidence that this kernel method can provide sufficient discrimination to predict various biological activities of a molecule with reasonable accuracy. Furthermore, together with a kernel feature space algorithm, experiments also provide convincing empirical evidence that our VSMMD can provide sufficient information to identify different binding modes with high accuracy.